基于生成式人体先验的时尚风格编辑
Fashion Style Editing with Generative Human Prior
AI总结：
本文提出时尚风格编辑框架FaSE，利用生成式人体先验在潜在空间中导航，并通过文本增强和视觉参照强化引导，实现基于文本描述的人物时尚风格编辑。
摘要：
图像编辑长期以来一直是研究界面临的一项挑战，并对众多应用产生深远影响。近年来，文本驱动的方法开始在人类面部等领域取得有前景的结果，但它们在更复杂领域中的应用相对有限。在本工作中，我们探索时尚风格编辑任务，旨在利用文本描述来操纵人物图像的时尚风格。具体而言，我们利用一种生成式人体先验，并通过在其学习到的潜在空间中进行导航来实现时尚风格编辑。我们首先验证了现有的文本驱动编辑方法由于引导信号过于简化而无法胜任我们的问题，并提出两个方向来强化引导：文本增强和视觉参照。结合我们对潜在空间结构的实证发现，我们的时尚风格编辑框架（FaSE）成功地将抽象时尚概念投射到人物图像上，并为该领域引入了令人兴奋的新应用。
英文摘要：
Image editing has been a long-standing challenge in the research community with its far-reaching impact on numerous applications. Recently, text-driven methods started to deliver promising results in domains like human faces, but their applications to more complex domains have been relatively limited. In this work, we explore the task of fashion style editing, where we aim to manipulate the fashion style of human imagery using text descriptions. Specifically, we leverage a generative human prior and achieve fashion style editing by navigating its learned latent space. We first verify that the existing text-driven editing methods fall short for our problem due to their overly simplified guidance signal, and propose two directions to reinforce the guidance: textual augmentation and visual referencing. Combined with our empirical findings on the latent space structure, our Fashion Style Editing framework (FaSE) successfully projects abstract fashion concepts onto human images and introduces exciting new applications to the field.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
